Deep 3D Face Identification
This addresses the lack of large-scale 3D face datasets for training discriminative deep features, enabling scalable 3D identification for applications like security or biometrics, though it is incremental as it builds on existing 2D methods.
The paper tackles the problem of 3D face recognition by using transfer learning from a CNN trained on 2D images and a 3D augmentation technique, achieving excellent recognition results on datasets like Bosphorus, BU-3DFE, and 3D-TEC without hand-crafted features.
We propose a novel 3D face recognition algorithm using a deep convolutional neural network (DCNN) and a 3D augmentation technique. The performance of 2D face recognition algorithms has significantly increased by leveraging the representational power of deep neural networks and the use of large-scale labeled training data. As opposed to 2D face recognition, training discriminative deep features for 3D face recognition is very difficult due to the lack of large-scale 3D face datasets. In this paper, we show that transfer learning from a CNN trained on 2D face images can effectively work for 3D face recognition by fine-tuning the CNN with a relatively small number of 3D facial scans. We also propose a 3D face augmentation technique which synthesizes a number of different facial expressions from a single 3D face scan. Our proposed method shows excellent recognition results on Bosphorus, BU-3DFE, and 3D-TEC datasets, without using hand-crafted features. The 3D identification using our deep features also scales well for large databases.